Open-Weight LineageUpstage

Upstage releases SOLAR 10.7B

Released SOLAR 10.7B — built by depth up-scaling (DUS) an open-source 7B model and pretrained on over 3T tokens; base model under Apache 2.0, instruction-tuned model under CC BY-NC 4.0

Why it matters

A model from a Korean startup that, per Upstage, topped the Hugging Face Open LLM Leaderboard at release; the 74.2 average belonged to the instruction-tuned SOLAR-10.7B-Instruct, while the base model scored 66.04

Source — Primary sources first; secondary reports are labelled “Press”

Officialupstage.aihttps://www.upstage.ai/news/solar-10-7b-emerges-as-worlds-top-pre-trained-llm

Added in Week 41, 2026 · See that week

Same week

Weak-to-strong generalizationOfficialSGLang paperPaperMixtral 8x7BOfficial

Nearby on the same axis

Mixtral 8x7BOfficialDeepSeek releases DeepSeek LLM 7B and 67BOfficialGemma 1 (2B/7B), under Gemma's own terms of usePressMistral AI launches Mistral LargeOfficial